Upload 11 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "dbmdz/bert-base-turkish-128k-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e69e5dccb16452505104ed541ac29e0edd9152942bc39b36648d766c4ca87a
+size 737411072

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f962701a7e656b52e861cb2ebe58723b56a3b7ac287807b9a3ae9238fa6f157f
+size 1474937594

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d32051101ec51c2b04c4ee6a6d2c7f40562e56836cbb02d6e6e3126490484d
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d26d72a04dea63c4863ddac8fbf2a43edf7989133960bf38b381b19d4a05d436
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.32348373532295227,
+  "best_model_checkpoint": "fine_tuned_turkish_bert10k/checkpoint-1112",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1668,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8992805755395683,
+      "grad_norm": 6.453958034515381,
+      "learning_rate": 1.4004796163069546e-05,
+      "loss": 0.2199,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9127697841726619,
+      "eval_loss": 0.3523901700973511,
+      "eval_runtime": 11.2517,
+      "eval_samples_per_second": 197.66,
+      "eval_steps_per_second": 12.354,
+      "step": 556
+    },
+    {
+      "epoch": 1.7985611510791366,
+      "grad_norm": 24.75876235961914,
+      "learning_rate": 8.00959232613909e-06,
+      "loss": 0.1617,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9154676258992805,
+      "eval_loss": 0.32348373532295227,
+      "eval_runtime": 11.2709,
+      "eval_samples_per_second": 197.323,
+      "eval_steps_per_second": 12.333,
+      "step": 1112
+    },
+    {
+      "epoch": 2.697841726618705,
+      "grad_norm": 0.4041008949279785,
+      "learning_rate": 2.0143884892086333e-06,
+      "loss": 0.1104,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9172661870503597,
+      "eval_loss": 0.3766934275627136,
+      "eval_runtime": 11.4325,
+      "eval_samples_per_second": 194.533,
+      "eval_steps_per_second": 12.158,
+      "step": 1668
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1668,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1755082294778880.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf53f66687c89cd5d12102c6b3e1313bee1850cfd28e11b122c0d21dc5bed1c
+size 5240